clinical trial management

Learn more about Medidata: https://www.medidata.com/en/

What trends have you seen in imaging in 2019?

One of the biggest trends has been an increase in demand for imaging over the last year as more and more trials have begun to require imaging as a primary endpoint. This has always been common in oncology studies in particular, but not the industry is starting to use imaging as a primary endpoint in other indications as well.

What do you think the future looks like?

In 2020 and beyond, there will be a push toward siteless trials. In imaging, we may be able to use subjects who live far from a primary site and previously would have had to travel for imaging. They’ll be able to visit a local center for imaging instead, and have those images uploaded remotely to a platform for centralized assessment. In fact, ERT’s platform allows this already: sites and local centers are able to complete uploads.

How has artificial intelligence had an impact on imaging?

We can use artificial intelligence to determine whether or not an image is appropriate. By using the information we’ve gathered over the past 15 years, we’ve trained an AI algorithm to determine the quality of an image. AI can also pre-segment images and so readers don’t define boundaries within the image themselves. This reduces variability and gives sponsors additional information that they may not have gotten from simplified criteria. Artificial intelligence can be used to improve efficiency and cost, and also maximizes the data being collected, which is particularly important when a patient is being exposed to radiation during the imaging process.

Introduction [00:50]

We welcome Jean-Phillippe Couderc from VPG Medical as he joins Trial Better to discuss passive health monitoring and VPG Medical’s technology, HealthKam.

What is passive health monitoring? [02:02]

Passive health monitoring, or opportunistic monitoring, embeds sensors that measure data into technologies or devices that are already used by the patient in everyday life, like smartphones, bath mats, and toilet seats. These devices place minimal constraints on the patient whereas with typical home or remote monitoring technology, patients are required to take care of the device. For example, a patient using an Apple Watch still has to charge the device and remember to wear it every day. Passive monitoring addresses this challenge.

What are some of the challenges of passive health monitoring?[04:25]

Since passive monitoring technologies don’t disrupt the patient’s lifestyle or require any behavioral changes, you need to ensure the sensors will be used consistently in other ways. This requires identification of devices that the patient naturally uses on a daily basis, which may change based on certain demographics or the patient’s routine.

How do we ensure high-quality data from opportunistic monitoring?[06:50]

With regular monitoring, you have more reliable, good quality data (for example, measurements from an ECG electrode making direct contact with the skin.) However, these methods also have shorter monitoring periods with physical constraints. ECG patches can only be used for up to 15 days because the connection between the skin and electrode loses viability.

With passive monitoring, the sensor is far from the patient, so external factors have more of an impact and you have less control over the data quality. However, artificial intelligence algorithms can be used to identify which data is actually valuable. Because passive health monitoring constantly collects data, you have hundreds of measurements; even if 50% of the measurements aren’t usable, you still have enough valid data.

How do patients feel about privacy with passive data collection? [09:03]

Technology today is designed so the patient’s information can be kept private, and there are solutions to avoid sharing PHI. For example, data can be encrypted, or technologies can be designed to collect only information related to the study (and not the patient’s name, address, etc.) Data privacy is changing, and the relationship consumers have with their data is, as well; patients are more comfortable with sharing their data than ever before. In some cases, patients who are terminally ill may be willing to sacrifice their privacy because the potential value of the information collected outweighs their concerns.

What is HealthKam? [11:45]

HealthKam uses the cameras embedded into smart devices to monitor your face and extract information about your pulse. As the quality of these cameras has increased, it has paved the way for passive health monitoring solutions like HealthKam. Each time your heart beats, it effects your blood pressure and causes a subtle change in the color of your facial skin. HealthKam’s unique technology detects these changes and extracts the person’s heart rate without touching them.

How does HealthKam work? [14:16]

HealthKam uses facial recognition to identify the patient, and then passively runs in the background while the patient uses their device. This technology isn’t restricted to smartphones (which patients may only use for short periods of time), but other devices like tablets, which may be used for longer periods, such as the duration of a movie or TV episode.

How will passive health monitoring impact the clinical research industry?[17:00]

Most arguments focus on the burden micropayments can put on sites. It’s yet another technology that sites have to engage in, and it can be difficult to go through the set-up process and train staff. However, sponsors need to consider these things not just with micropayments, but all with technology, so it’s important to take a step back and determine if micropayments can provide a benefit to the trial.

Introduction [00:20]

Phil Lake and Dr. Kai Michael-Beeh examine the steps sponsors and study teams can take to improve data quality and reduce data variability in respiratory trials. They also discuss the innovations and trends they expect to see in the industry in the future.

How can sponsors and the pharma industry overcome unacceptable data variability from sites? [03:30]

Respiratory measurements can be complicated and challenging if study teams don’t stick to the fundamentals. This means that variability and bad data quality are common issues. Two major factors can contribute to variability: disease-associated factors and effort-dependent factors. Both of these issues can be managed, with strict standardization in the protocol and rigorous training, respectively.

Is a focus on ATS/ERS standards enough to generate research-grade data? [06:34]

ATS/ERS standards are a suitable starting point and principle for quality assurance. However, simply applying these rules is not sufficient. In addition to following these standards, sponsors should implement additional visual inspections and plausibility checks.

How can we use available technology and services to reduce data variability? [09:50]

Available technology and data should be used to guarantee the production of the highest quality data possible. Ensure that investigators are aware of what defines a good quality test in the context of a clinical trial, including how important it is to show changes in lung function. Increased overall communication with investigators decreases variability, as well as the number of patients needed (and ultimately costs.)

How can sponsors and sites best stay on track with projected timelines? [14:35]

Communicating with sites so they can more effectively allocate their resources, especially when a study has fallen behind, can be a crucial improvement. Checks should take place to ensure that third-party providers are ready to begin once the site is initiated.

What’s the real cost or impact to pharma when we produce variable data or run into study delays? [19:18]

Variable data and study delays have a tremendous impact by putting approvals at risk and jeopardizing the reputation of the drug or manufacturer. When studies produce better data, there’s an increased chance of achieving study goals with less patients and lower costs. Better data also improves confidence in negative results.

Any future innovations that will improve data quality? How can we do better as an industry to understanding drug effect? [21:38]

In the future, the ability to measure various aspects of airway function will improve due to the shift towards personalized medicine, with new methods regulated and approved by the FDA.

Patricia Castellano and Emily Olsson explore how sites can benefit from developing a stronger relationship with their ABPM device vendors. They also address strategies for successful repeat ABPM sessions when a patient is non-compliant, and how ABPM achieves a type of holistic data not possible with other BP measurement methods.

Introduction [00:37]
Patricia Castellano, Senior Director of Product Management at ERT, is joined by Emily Olsson, CCRP, from the University of North Carolina Chapel Hill for an in-depth look at the keys to implementing a successful ABPM protocol in a cardiac safety trial.

Improving ABPM through Better Site/Vendor Relationships [04:10]
Sites that don’t have much experience with ABPM shouldn’t hesitate to reach out to device manufacturers to ask for training or assistance when needed. Other external teams and experts may also be willing to provide ABPM insights. Vendors who can provide customizable software with easy-to-read outputs are ideal.

Achieving Successful ABPM Repeat Sessions [07:37]
If a patient is non-compliant or produces unusable data, a repeat ABPM session may need to be scheduled. Discuss the outcome of the original session with the patient and identify how the experience can be improved. Proactively manage the expectations of individuals in patient groups that may experience repeat inflations – such as elderly or obese patients – and provide them with tips and tricks that can help improve their comfort and compliance.

Using Home Blood Pressure Monitoring (HBPM) Instead of ABPM Comparing Compliance with ABPM to Other Blood Pressure Monitoring Methods [12:01]
Home blood pressure monitoring provides more comprehensive blood pressure data than a single measurement in the clinic. However, patients are typically not well-educated on how to use a home blood pressure device and may fall out of compliance over the duration of the collection period. This results in data that isn’t a true reflection of their blood pressure.

Drew Bustos, Senior Director of Business Intelligence Products, is joined by Dr. Santikary, Vice President and Global Chief Data Officer at ERT, for a discussion of the role of modern data architecture. Clinical trial sponsors and CROs are facing increasing numbers of complex data integration and quality challenges. Are you struggling to keep up with this exponential data growth? The solution may lie in modern data platform, cloud, and artificial intelligence technologies.

Data Architecture Challenges in Clinical Trials & Healthcare
Data architecture challenges can be significant, and often include data security; data privacy and protection at scale; data integration at scale; real time reporting and analytics at scale; and data governance and master data management at scale. A modern data platform can be built to handle these challenges.

Common Data Integration Problems
Integrating data and serving it to the end user in one, centralized location is easier said than done. Different vendors and technologies, using disparate platforms, make the integration process even more difficult. In addition to a lack of standardization, unstructured data and binary data further compound the data integration and architecture challenges.

Emerging Trends in Data Architecture and Technologies in the Clinical Trial and Healthcare Industries
The rate of change in clinical research and healthcare technology is unprecedented. In particular, artificial intelligence and blockchain technology are making a huge impact in clinical research.

The State of Artificial Intelligence and its Clinical Trial Application
Sponsors and CROs can expect to see a major shift toward embracing AI in the pharma industry over the next few years. In fact, this trend has already begun with the use of predictive algorithms, chatbots, and voicebots in clinical trials. Artificial intelligence has the potential to accelerate drug discovery and increase trial efficiency.